Back to AIBriefs
LaunchAI Models

Google releases Gemma 4 12B QAT GGUF model

Google released a 4-bit quantized version of its Gemma 4 12B instruction-tuned model, using quantization-aware training (QAT) and GGUF format. The model is available on HuggingFace with 57 likes and over 4,600 downloads.

·
Jun 5, 12:28 AM
Google releases Gemma 4 12B QAT GGUF model — AIBriefs